{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SW7M3AJS54KLEZPICNDT5P6VOM","short_pith_number":"pith:SW7M3AJS","schema_version":"1.0","canonical_sha256":"95becd8132ef14b265e813473ebfd5732a465c1de0aec258b91ca08fc7670e9b","source":{"kind":"arxiv","id":"2112.08804","version":3},"attestation_state":"computed","paper":{"title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Rifat Shahriyar, Tahmid Hasan, Wasi Uddin Ahmad, Yong-Bin Kang, Yuan-Fang Li","submitted_at":"2021-12-16T11:40:36Z","abstract_excerpt":"We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2112.08804","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:40:36Z","cross_cats_sorted":[],"title_canon_sha256":"3009a17fddcbad642074b3b43eb41d026469b5add8e2757608c3c2797d1bce38","abstract_canon_sha256":"7a796bf24857b1b93a508cc82cf171f8ee0890a66f97c8b0b6ddd5f8adbd0542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:03.268654Z","signature_b64":"0lzoPVDt10GLAjFZJHGu021TG33YtMfC1fbh5mpcO/Ir0xFMULhNRRC5qbsP7CZAuzooE4cuXj/ckqe5df7EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95becd8132ef14b265e813473ebfd5732a465c1de0aec258b91ca08fc7670e9b","last_reissued_at":"2026-07-05T06:14:03.268228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:03.268228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Rifat Shahriyar, Tahmid Hasan, Wasi Uddin Ahmad, Yong-Bin Kang, Yuan-Fang Li","submitted_at":"2021-12-16T11:40:36Z","abstract_excerpt":"We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08804","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.08804/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2112.08804","created_at":"2026-07-05T06:14:03.268284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08804v3","created_at":"2026-07-05T06:14:03.268284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08804","created_at":"2026-07-05T06:14:03.268284+00:00"},{"alias_kind":"pith_short_12","alias_value":"SW7M3AJS54KL","created_at":"2026-07-05T06:14:03.268284+00:00"},{"alias_kind":"pith_short_16","alias_value":"SW7M3AJS54KLEZPI","created_at":"2026-07-05T06:14:03.268284+00:00"},{"alias_kind":"pith_short_8","alias_value":"SW7M3AJS","created_at":"2026-07-05T06:14:03.268284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10590","citing_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM","json":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM.json","graph_json":"https://pith.science/api/pith-number/SW7M3AJS54KLEZPICNDT5P6VOM/graph.json","events_json":"https://pith.science/api/pith-number/SW7M3AJS54KLEZPICNDT5P6VOM/events.json","paper":"https://pith.science/paper/SW7M3AJS"},"agent_actions":{"view_html":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM","download_json":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM.json","view_paper":"https://pith.science/paper/SW7M3AJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08804&json=true","fetch_graph":"https://pith.science/api/pith-number/SW7M3AJS54KLEZPICNDT5P6VOM/graph.json","fetch_events":"https://pith.science/api/pith-number/SW7M3AJS54KLEZPICNDT5P6VOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM/action/storage_attestation","attest_author":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM/action/author_attestation","sign_citation":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM/action/citation_signature","submit_replication":"https://pith.science/pith/SW7M3AJS54KLEZPICNDT5P6VOM/action/replication_record"}},"created_at":"2026-07-05T06:14:03.268284+00:00","updated_at":"2026-07-05T06:14:03.268284+00:00"}